Previous | 
Home
Section: New Results
Visual servoing
Micro-manipulation
Participant : Eric Marchand.
We developed an accurate nanopositioning system based on direct visual servoing [43] ,[17] . This technique relies only on the pure image signal to design the control law, by using the pixel intensity of each pixel as visual features. The proposed approach has been tested in terms of accuracy and robustness in several experimental conditions. The obtained results have demonstrated a good behavior of the control law and very good positioning accuracy: 89 nm, 14 nm, and 0.001 degrees in the and axes of a positioning platform, respectively.
Multi sensor-based control
Participants : Olivier Kermorgant, François Chaumette.
We have designed a generic sensor-based control approach to automatically tune the weights related to the features involved as inputs of a control scheme, allowing to take constraints into account. This scheme has been applied to several confugirations, such as fusing the data provided by an eye-in-hand camera and an eye-to-hand camera, ensuring the visibility constraint, and avoiding the robot joint limits [30] , [31] , [32] , [11] .
Visual navigation of mobile robots
Participants : Eric Marchand, Andrea Cherubini, Fabien Spindler, François Chaumette.
We have developed a visual servoing scheme based on the mutual information between the images acquired by an onboard camera and a visual memory to control the orientation of a vehicle during its navigation [27] . We have also fused the data provided by a pan-tilt camera and a laser range sensor for the autonomous navigation of a mobile vehicle while avoiding obstacles [23] , [22] . Real experiments with our Cycab (see Section 5.4 ) have been conducted on Place de Jaude in Clermont-Ferrand in the scope of the ANR Tosa CityVIP project (See Section 8.2.1 ).
Visual servoing for aircrafts
Participants : Céline Teulière, Eric Marchand, Laurent Coutard, François Chaumette.
A dynamic controller has been designed for the homing of a quadri-rotor aerial vehicle [39] . A color-based tracking algorithm has also been designed and combined with an image-based visual servoing for chasing a moving target from a a flying UAV [44] . Finally, a method has been developed to detect and localize an aircrat carrier in an image sequence, from which visual servoing control laws have been designed for the automatic landing [25] , [26] .